Review-guided Helpful Answer Identification in E-commerce

TL;DR

This paper introduces RAHP, a model that predicts answer helpfulness in e-commerce QA by considering answer-review opinion coherence, outperforming traditional relevance-based methods.

Contribution

The paper proposes a novel review-guided approach that models opinion coherence as a language inference task, enhancing answer helpfulness prediction in e-commerce platforms.

Findings

RAHP outperforms baseline models in predicting answer helpfulness.

Incorporating review opinion coherence improves prediction accuracy.

Pre-training enhances the model's understanding of textual inference.

Abstract

Product-specific community question answering platforms can greatly help address the concerns of potential customers. However, the user-provided answers on such platforms often vary a lot in their qualities. Helpfulness votes from the community can indicate the overall quality of the answer, but they are often missing. Accurately predicting the helpfulness of an answer to a given question and thus identifying helpful answers is becoming a demanding need. Since the helpfulness of an answer depends on multiple perspectives instead of only topical relevance investigated in typical QA tasks, common answer selection algorithms are insufficient for tackling this task. In this paper, we propose the Review-guided Answer Helpfulness Prediction (RAHP) model that not only considers the interactions between QA pairs but also investigates the opinion coherence between the answer and crowds' opinions reflected in the reviews, which is another important factor to identify helpful answers. Moreover, we tackle the task of determining opinion coherence as a language inference problem and explore the utilization of pre-training strategy to transfer the textual inference knowledge obtained from a specifically designed trained network. Extensive experiments conducted on real-world data across seven product categories show that our proposed model achieves superior performance on the prediction task.